Sign up to save your podcasts
Or
Share Today's AIs Aren't Paperclip Maximizers. That Doesn't Mean They're Not Risky
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Today's AIs Aren't Paperclip Maximizers. That Doesn't Mean They're Not Risky
Classic arguments about AI risk imagined AIs pursuing arbitrary and hard-to-comprehend goals. Large language models aren't like that, but they pose risks of their own.
View all episodes
By Center for AI SafetyClassic arguments about AI risk imagined AIs pursuing arbitrary and hard-to-comprehend goals. Large language models aren't like that, but they pose risks of their own.